Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to scientific measurements and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quia
    -0.15
    fabs
    -0.15
    orte
    -0.15
    ictory
    -0.15
     frank
    -0.14
    acic
    -0.14
     indiv
    -0.14
    essaging
    -0.13
     ~
    -0.13
    utures
    -0.13
    POSITIVE LOGITS
     effect
    0.30
     effects
    0.29
     influence
    0.26
    effects
    0.26
     Effects
    0.26
     Influence
    0.25
    effect
    0.23
    Effects
    0.22
     Effect
    0.22
    -effects
    0.22
    Act Density 0.257%

    No Known Activations